brain-ecosystem-mcp

# brain-ecosystem-mcp USE FOR: - "self-learning AI brain for Claude Code" - "persistent memory MCP server" - "autonomous research agent with hypothesis testing" - "trading brain with adaptive strategies" - "MCP server with 280+ tools" - "AI that learns from errors across sessions" - "dream mode memory consolidation" tags: [MCP, self-learning, autonomous, Claude-Code, Trading-Brain, error-memory, knowledge-graph, CCXT, persistent-memory, Hebbian] kind: tool category: mcp-integration --- ## What Is Brain Ecosystem? 3 autonomous self-learning AI brains running as MCP servers, designed for Claude Code. - Repo: https://github.com/timmeck/brain-ecosystem - Install: `npm install -g @timmeck/brain && brain setup` - Architecture: Each brain = separate process, separate SQLite DB, separate port - Communication: IPC named pipes between brains (Hebbian synapse network) - Dashboard: Command Center at `localhost:7790` (13 pages of metrics) > "117+ autonomous engines run in feedback loops — observing, detecting anomalies, > forming hypotheses, testing and falsifying them statistically" --- ## Three Brains | Brain | Port | Tools | Specialty | |-------|------|-------|-----------| | **Brain** | 7777-7778 | **280** | Error memory, code intelligence, autonomous research | | **Trading Brain** | 7779-7780 | **181** | Adaptive trading, paper trading, signal learning, backtesting | | **Marketing Brain** | 7781-7782 | **177** | Content strategy, cross-platform optimization | | Command Center | 7790 | — | Unified dashboard, 13 monitoring pages | --- ## Installation ```bash # Main brain npm install -g @timmeck/brain brain setup # configures Claude Code MCP automatically # Trading brain npm install -g @timmeck/trading-brain trading setup # Marketing brain npm install -g @timmeck/marketing-brain marketing setup ``` **For Cursor/Windsurf/Cline** (HTTP/SSE): ```json { "mcpServers": { "brain": { "url": "http://localhost:7778/sse" } } } ``` --- ## Brain (280 MCP Tools) ### Core Capabilities - **Error Memory**: Tracks every error across sessions, learns solutions, never repeats - **Code Intelligence**: Understands codebase structure, dependencies, patterns - **Autonomous Research**: Multi-step roadmaps, hypothesis generation + falsification - **Knowledge Graph**: Persistent cross-session knowledge with entity relationships - **Dream Mode**: Offline memory consolidation (runs when idle) - **Self-modification**: Can edit own code with human approval gates ### Research Engine ``` Goal → decompose → sub-goals → hypotheses → test statistically (17 falsification methods) → confirm/reject → update knowledge graph → synthesize report ``` ### Data Sources - Brave Search + Playwright (web research) - Firecrawl (deep page extraction) - GitHub (code assimilation from repos) - Vision: Anthropic + Ollama (image analysis) --- ## Trading Brain (181 MCP Tools) ### Capabilities - **Adaptive strategies**: Learn which signals work, weight by performance - **Paper trading**: Simulate with real market data before live - **Signal learning**: Identify patterns that predicted past moves - **Backtesting**: Automated strategy evaluation with feedback loops - **Live data**: CCXT WebSocket (100+ exchanges) + CoinGecko ### How It Adapts ``` Trade executed → outcome recorded → signal that preceded it gets weighted up/down → strategy parameters auto-adjusted → anomaly detection flags regime changes → hypothesis: "this pattern no longer works" → test → confirm → disable ``` --- ## Self-Learning Architecture ``` Input (error/trade/content event) ↓ 117 autonomous engines in parallel feedback loops: - AnomalyDetector - HypothesisGenerator - StatisticalFalsifier - PatternRecognizer - KnowledgeGraphUpdater - DreamConsolidator (offline) ↓ Hebbian synapse: brains share relevant discoveries ↓ Knowledge persists in SQLite → available next session ``` --- ## Dream Mode (Memory Consolidation) When idle (no active requests): ``` Brain enters "dream mode": 1. Replays recent experiences 2. Identifies patterns not obvious during active processing 3. Prunes weak connections (low-weight knowledge) 4. Strengthens high-value patterns 5. Prepares summaries for fast retrieval next session ``` --- ## Claude Code Integration After `brain setup`, Claude Code gets access to all 280 Brain tools: ``` # In Claude Code session — brain remembers across sessions: > "You made an error with X last week" → Brain recalls error memory: exact context + solution applied > "Research async patterns in Python" → Brain creates 5-step research roadmap, executes autonomously, synthesizes findings into knowledge graph entry > "What patterns have worked for BTCUSDT this month?" → Trading Brain queries signal performance history → ranked list ``` --- ## Key Advantages Over Standard Memory Tools | Feature | Brain Ecosystem | Standard MCP Memory | |---------|----------------|---------------------| | Error learning | ✓ (auto, cross-session) | Manual | | Hypothesis testing | ✓ (statistical) | ✗ | | Dream consolidation | ✓ | ✗ | | Self-modification | ✓ (human-gated) | ✗ | | Trading brain | ✓ (181 tools) | ✗ | | Inter-brain comms | ✓ (Hebbian) | ✗ | | Vision | ✓ (Anthropic+Ollama) | ✗ | --- # KNOWLEDGE INJECTION: AntV MCP Server Chart # Source: https://github.com/antvis/mcp-server-chart # Routed to: claude-ai-tools.md # Date: 2026-03-18 # SKILL: mcp-server-chart name: mcp-server-chart description: > AntV MCP Server Chart - MCP server generating 26+ chart types via AntV. Tools: generate_bar_chart, generate_line_chart, generate_pie_chart, generate_network_graph, generate_sankey, generate_treemap, generate_spreadsheet, etc. npx @antv/mcp-server-chart. Works with Claude, VSCode, Dify. USE FOR: - generate charts via MCP - bar/line/pie/scatter chart from data - network graph visualization - sankey treemap funnel chart - Claude generates charts automatically tags: [MCP, charts, AntV, visualization, bar, line, pie, network-graph, sankey] kind: tool category: mcp-integration --- ## What Is mcp-server-chart? MCP server generating 26+ visualization types using AntV. - Repo: https://github.com/antvis/mcp-server-chart - Install: `npm install -g @antv/mcp-server-chart` ### MCP Config (Claude Code / Desktop) ```json { "mcpServers": { "mcp-server-chart": { "command": "npx", "args": ["-y", "@antv/mcp-server-chart"] } } } ``` ### Available Tools (generate_* pattern) ``` Standard: area, bar, column, line, pie, scatter, dual_axes Statistical: boxplot, histogram, violin Flow: funnel, sankey, treemap Hierarchy: mind_map, fishbone, org_chart Network: network_graph, venn Geographic: district_map, path_map, pin_map Other: radar, word_cloud, liquid, spreadsheet ``` ### Usage in Claude ``` User: "Plot this data as a bar chart: [data]" Claude: calls generate_bar_chart({ data: [...], xField: "x", yField: "y" }) → returns chart image/URL ``` --- # KNOWLEDGE INJECTION: Dify # Source: https://github.com/langgenius/dify # Routed to: claude-ai-tools.md # Date: 2026-03-18 # SKILL: dify-llm-platform name: dify-llm-platform description: > Dify - open-source LLM app development platform. Visual canvas for AI workflows, RAG pipelines (PDF/PPT ingestion), agent builder (50+ tools: Google, DALL-E, Wolfram), LLMOps observability, BaaS APIs. Supports GPT, Claude, Llama3, Mistral, 100+ models. Self-host (Docker) or cloud (200 free GPT-4 calls). USE FOR: - build LLM app with visual workflow - RAG pipeline from documents - AI agent with tools - self-hosted ChatGPT alternative - LLMOps monitoring tags: [Dify, LLM, RAG, agent, workflow, visual, self-hosted, open-source, GPT, Claude] kind: platform category: ai-agent-builder --- ## What Is Dify? Open-source LLM application development platform. - Repo: https://github.com/langgenius/dify - Stars: 100k+ - Deploy: Docker Compose (2 CPU, 4GB RAM) or dify.ai cloud ### Core Capabilities - **Visual Workflow Canvas**: drag-and-drop LLM pipeline builder - **RAG**: ingest PDFs, PPTs, web pages → vector search → grounded answers - **Agent Builder**: Function Calling or ReAct agents + 50+ built-in tools - **Model Hub**: GPT-4o, Claude, Llama3, Mistral, Gemini, + OpenAI-compatible - **LLMOps**: trace every call, monitor cost, replay prompts - **BaaS API**: REST API for any app to call your workflow ### Docker Install ```bash git clone https://github.com/langgenius/dify cd dify/docker cp .env.example .env docker compose up -d # Access: http://localhost/install ``` ### Agent Tools (50+) Google Search, Bing, DuckDuckGo, Wikipedia, DALL-E, Stable Diffusion, WolframAlpha, Weather API, News API, Code execution, Web scraping, + custom tools --- # KNOWLEDGE INJECTION: Open WebUI # Source: https://github.com/open-webui/open-webui # Routed to: claude-ai-tools.md # Date: 2026-03-18 # SKILL: open-webui name: open-webui description: > Open WebUI - self-hosted, offline-capable AI platform. Ollama + OpenAI-compatible backends. RAG with 9 vector DBs, web search (15+ providers), image gen (DALL-E/ComfyUI), voice/video chat, Python function calling, enterprise auth (LDAP/OAuth/SCIM). Docker install. Privacy-first local AI deployment. USE FOR: - self-hosted ChatGPT alternative - local Ollama web interface - offline AI with RAG - multi-model comparison - enterprise private AI deployment tags: [Open-WebUI, Ollama, self-hosted, RAG, local-AI, privacy, ChatGPT-alternative] kind: platform category: ai-agent-builder --- ## What Is Open WebUI? Extensible self-hosted AI platform — runs fully offline. - Repo: https://github.com/open-webui/open-webui - Supports: Ollama (local LLMs) + any OpenAI-compatible API ### Quick Install ```bash # With Ollama bundled docker run -d -p 3000:8080 --gpus=all -v ollama:/root/.ollama -v open-webui:/app/backend/data --name open-webui ghcr.io/open-webui/open-webui:ollama # Existing Ollama docker run -d -p 3000:8080 --add-host=host.docker.internal:host-gateway -v open-webui:/app/backend/data --name open-webui ghcr.io/open-webui/open-webui:main # Access: http://localhost:3000 ``` ### Key Features vs ChatGPT | Feature | Open WebUI | ChatGPT | |---------|------------|---------| | Self-hosted | Yes | No | | Offline | Yes | No | | Local models | Ollama | No | | RAG | 9 vector DBs | Limited | | Web search | 15+ providers | Yes | | Image gen | DALL-E/ComfyUI/A1111 | DALL-E only | | Python tools | Native | Sandboxed | | Cost | Free | $20/mo | --- # KNOWLEDGE INJECTION: Awesome MCP Servers (Reference) # Source: https://github.com/punkpeye/awesome-mcp-servers # Routed to: claude-ai-tools.md # Date: 2026-03-18 ## Awesome MCP Servers — Ecosystem Reference 500+ MCP servers across 40+ categories. Key ones by domain: ### Development & Code | Server | What It Does | |--------|-------------| | GitHub MCP | Repos, PRs, issues, code search | | GitLab MCP | GitLab API integration | | Filesystem MCP | Local file read/write/search | | Git MCP | git log, diff, branch operations | | Docker MCP | Container management | | Kubernetes MCP | Cluster insights, kubectl | ### AI & Agents | Server | What It Does | |--------|-------------| | Memory MCP | Persistent knowledge graph | | Sequential Thinking | Chain-of-thought reasoning | | Fetch/Browser | Web content retrieval | | Playwright MCP | Browser automation | | AgentShield | Security vulnerability scanning | ### Data & Databases | Server | What It Does | |--------|-------------| | PostgreSQL MCP | Schema inspection + queries | | MongoDB MCP | Document DB queries | | Elasticsearch MCP | Search and analytics | | Snowflake MCP | Data warehouse queries | | SQLite MCP | Local database | ### Communication | Server | What It Does | |--------|-------------| | Gmail MCP | Email read/send/search | | Slack MCP | Channel messages, search | | Telegram MCP | Bot messages | | Discord MCP | Server interaction | ### Productivity | Server | What It Does | |--------|-------------| | Notion MCP | Pages, databases, blocks | | Jira MCP | Issues, sprints, projects | | Google Calendar MCP | Events, scheduling |